# Parallel Unlearning in Inherited Model Networks

arXiv: https://arxiv.org/abs/2408.08493 · HTML: https://mlsanity.com/paper/2408.08493/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 16 Aug 2024.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 24 of 24)

- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection](https://mlsanity.com/paper/1907.09693/) (2019)
- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)
- [Towards Unbounded Machine Unlearning](https://mlsanity.com/paper/2302.09880/) (2023)
- [Fast Yet Effective Machine Unlearning](https://mlsanity.com/paper/2111.08947/) (2021)
- [Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening](https://mlsanity.com/paper/2308.07707/) (2023)
- [Variational Bayesian Unlearning](https://mlsanity.com/paper/2010.12883/) (2020)
- [VeriFi: Towards Verifiable Federated Unlearning](https://mlsanity.com/paper/2205.12709/) (2022)
- [Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection](https://mlsanity.com/paper/2312.04095/) (2023)
- [Layer-wise Adaptive Model Aggregation for Scalable Federated Learning](https://mlsanity.com/paper/2110.10302/) (2021)
- [Communication Efficient and Provable Federated Unlearning](https://mlsanity.com/paper/2401.11018/) (2024)
- [An Information Theoretic Approach to Machine Unlearning](https://mlsanity.com/paper/2402.01401/) (2024)
- [IronForge: An Open, Secure, Fair, Decentralized Federated Learning](https://mlsanity.com/paper/2301.04006/) (2023)
- [Distill to Delete: Unlearning in Graph Networks with Knowledge Distillation](https://mlsanity.com/paper/2309.16173/) (2023)
- [Decoupling the Class Label and the Target Concept in Machine Unlearning](https://mlsanity.com/paper/2406.08288/) (2024)
- [Data Selection for Transfer Unlearning](https://mlsanity.com/paper/2405.10425/) (2024)
- [Split Unlearning](https://mlsanity.com/paper/2308.10422/) (2023)
- [eCIL-MU: Embedding based Class Incremental Learning and Machine Unlearning](https://mlsanity.com/paper/2401.02457/) (2024)
- [BlockFUL: Enabling Unlearning in Blockchained Federated Learning](https://mlsanity.com/paper/2402.16294/) (2024)

## Built on by (most cited first, 1 of 1)

- [Exploring Incremental Unlearning: Techniques, Challenges, and Future Directions](https://mlsanity.com/paper/2502.16708/) (2025)

## Abstract (arXiv)

Unlearning is challenging in generic learning frameworks with the continuous growth and updates of models exhibiting complex inheritance relationships. This paper presents a novel unlearning framework that enables fully parallel unlearning among models exhibiting inheritance. We use a chronologically Directed Acyclic Graph (DAG) to capture various unlearning scenarios occurring in model inheritance networks. Central to our framework is the Fisher Inheritance Unlearning (FIUn) method, designed to enable efficient parallel unlearning within the DAG. FIUn utilizes the Fisher Information Matrix (FIM) to assess the significance of model parameters for unlearning tasks and adjusts them accordingly. To handle multiple unlearning requests simultaneously, we propose the Merging-FIM (MFIM) function, which consolidates FIMs from multiple upstream models into a unified matrix. This design supports all unlearning scenarios captured by the DAG, enabling one-shot removal of inherited knowledge while significantly reducing computational overhead. Experiments confirm the effectiveness of our unlearning framework. For single-class tasks, it achieves complete unlearning with 0% accuracy for unlearned labels while maintaining 94.53% accuracy for retained labels. For multi-class tasks, the accuracy is 1.07% for unlearned labels and 84.77% for retained labels. Our framework accelerates unlearning by 99% compared to alternative methods. Code is in https://github.com/MJLee00/Parallel-Unlearning-in-Inherited-Model-Networks.